AMD Radeon Instinct MI250 vs Intel Data Center GPU Max 1550

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs Intel Data Center GPU Max 1550 with 128 GB HBM2e and 16,384 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI250

AMD Radeon Instinct MI250

RX 7900 XTX RX 7900 XTX
Instinct MI300X Instinct MI300X
MI250 MI250

Intel Data Center GPU Max 1550

55.2

Intel Data Center GPU Max 1550

55.2

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks Additional

Memory

Memory Size

128 GB
🔥 128 ГБ

Memory Type

HBM2e HBM2e

Memory Bandwidth

3.28 TB/s
🔥 3.28 TB/s

Memory Bus Width

8,192 бит 8,192 бит

ML Performance

FP16 (Half Precision)

362.1 TFLOPS
🔥 52.43 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

45.26 TFLOPS
🔥 +16% 52.43 TFLOPS

FP64 (Double Precision)

45.26 TFLOPS
🔥 +16% 52.43 TFLOPS

CUDA Cores

13,312
🔥 +23% 16,384

RT Cores

No
🔥 128

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Generation 12.5

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No No

Clocks & Performance

Base Clock

1,000
🔥 900

Boost Clock

1,700
🔥 1,600

Memory Clock

1,600
🔥 1,600

Power Consumption

TDP/TGP

🔥 -17% 500 W
600 W

Recommended PSU

🔥 -10% 900 W
1000 W

Power Connector

2x 8-pin No

Rendering

Texture Units (TMU)

832
🔥 +23% 1,024

ROP

No
🔥 128

L2 Cache

16 MB
🔥 +2,450% 408 MB

Benchmarks

llama.cpp, llama-2-7b-Q4_0

63.9 tokens/s

Additional

Slots

Dual-slot OAM Module

Release Date

Nov. 8, 2021 Jan. 10, 2023

Display Outputs

No outputs
No outputs

Renting is cheaper than buying